• Evolution of Neural Networks for Physically Simulated Evolved Virtual Quadruped Creatures

      Vaughan, Neil; Royal Academy of Engineering; University of Chester (Springer-Verlag, 2018-07-07)
      This work develops evolved virtual creatures (EVCs) using neuroevolution as the controller for movement and decisions within a 3D physics simulated environ-ment. Previous work on EVCs has displayed various behaviour such as following a light source. This work is focused on complexifying the range of behaviours available to EVCs. This work uses neuroevolution for learning specific actions combined with other controllers for making higher level decisions about which action to take in a given scenario. Results include analysis of performance of the EVCs in simulated physics environment. Various controllers are compared including a hard coded benchmark, a fixed topology feed forward artificial neural network and an evolving ANN subjected to neuroevolution by applying mutations in both topology and weights. The findings showed that both fixed topology ANNs and neuroevolution did successfully control the evolved virtual creatures in the distance travelling task.
    • Morphogenetic Engineering For Evolving Ant Colony Pheromone Communication

      Vaughan, Neil; University of Chester (The Society for the Study of Artificial Intelligence and Simulation for Behaviour (AISB), 2018-04-06)
      This research investigates methods for evolving swarm communication in a simulated colony of ants using pheromone when foriaging for food. This research implemented neuroevolution and obtained the capability to learn pheromone communication autonomously. Building on previous literature on pheromone communication, this research applies evolution to adjust the topology and weights of an artificial neural network which controls the ant behaviour. Comparison of performance is made between a hard-coded benchmark algorithm, a fixed topology ANN and neuroevolution of the ANN topology and weights. The resulting neuroevolution produced a neural network which was successfully evolved to achieve the task objective, to collect food and return it to the nest.
    • Multi-Agent Reinforcement Learning for Swarm Retrieval with Evolving Neural Network

      Vaughan, Neil; Royal Academy of Engineering; University of Chester (Springer-Verlag,, 2018-07-07)
      This research investigates methods for evolving swarm communica-tion in a sim-ulated colony of ants using pheromone when foriaging for food. This research implemented neuroevolution and obtained the capability to learn phero-mone communication autonomously. Building on previous literature on phero-mone communication, this research applies evolution to adjust the topology and weights of an artificial neural network (ANN) which controls the ant behaviour. Compar-ison of performance is made between a hard-coded benchmark algorithm (BM1), a fixed topology ANN and neuroevolution of the ANN topology and weights. The resulting neuroevolution produced a neural network which was suc-cessfully evolved to achieve the task objective, to collect food and return it to a location.